Deep learning microscope for slide-free and digital histology

用于无载玻片和数字组织学的深度学习显微镜

• 批准号: 10664026
• 负责人: Ann M Gillenwater
• 金额: $ 70.11万
• 依托单位: RICE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-12 至 2027-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10664026
• 关键词: Address; Algorithms; Anatomy; Area; Artificial Intelligence; Cellular Morphology; Classification; Clinical; Clinical Data; Clinical Research; Computer Assisted; Computer-Assisted Diagnosis; Consumption; Diagnosis; Diagnostic; Dyes; Ensure; Equipment; Excision; Formalin; Freezing; Fresh Tissue; Frozen Sections; Goals; Hematoxylin and Eosin Staining Method; Histology; Histopathology; Human Resources; Image; Image Analysis; Image-Guided Surgery; Improve Access; Lateral; Light Microscope; Lighting; Malignant Neoplasms; Manuals; Maps; Masks; Mechanics; Methods; Microscope; Microscopy; Microtome - medical device; Monitor; Mouth Neoplasms; Normal tissue morphology; Nuclear; Operative Surgical Procedures; Optics; Oral Surgical Procedures; Paraffin; Pathologist; Pathology; Patient Care; Patient-Focused Outcomes; Patients; Performance; Play; Population; Preparation; Procedures; Process; Protocols documentation; Recurrence; Resected; Resolution; Resource-limited setting; Resources; Role; Rural; Sampling; Scanning; Services; Slice; Slide; Specific qualifier value; Specimen; Speed; Stains; Surface; Surgeon; Survival Rate; System; Technology; Testing; Thick; Thinness; Time; Tissue Sample; Tissue imaging; Tissues; Training; Ultraviolet Rays; Variant; absorption; algorithm training; automated algorithm; cancer surgery; cancer survival; cellular imaging; clinical infrastructure; contrast imaging; cryostat; deep learning; design; digital; disease diagnosis; experience; fabrication; fluorescence microscope; graphical user interface; health care quality; histopathological examination; improved; innovation; instrument; learning network; light emission; low and middle-income countries; machine learning algorithm; machine learning framework; malignant mouth neoplasm; meter; mouth squamous cell carcinoma; novel; optical imaging; point of care; programs; reconstruction; research clinical testing; scalpel; survival outcome; tissue processing; tool; tumor; ultraviolet; virtual

Project summary/abstract: Anatomic histopathology plays a central role in disease diagnosis and in surgical procedure guidance to ensure delivery of quality healthcare and treatment. At the time of surgery, for example, tumor margins are ideally assessed with fast frozen section pathology to help ensure complete tumor resection while sparing normal tissue. Unfortunately, the time- and labor-intensive slide preparation process requires expensive equipment and specialized personnel, so it is not widely available in many settings including the rural US; even in settings with the clinical infrastructure to perform frozen section, only a small fraction of the margin is manually examined. In resource-limited global settings, a dire shortage of pathologists makes it more challenging to provide routine diagnostic pathology. Therefore, there is a critical need for affordable tools to support quality histopathology programs throughout the world. The goal of this proposal is to use recent advances in optical fabrication and artificial intelligence to develop a new and affordable tool, the deep learning extended depth-of-field (DeepDOF) platform, to rapidly examine fresh tissue resections without extensive slide preparation, while providing computer-aided image analysis at the point of care. We will demonstrate and validate its use for tumor margin assessment in patients with oral squamous cell carcinoma, the sixth most common malignancy worldwide. In Aim 1, we will develop key modules of the DeepDOF platform for rapid, subcellular imaging of freshly resected tissue samples. A deep learning network will be developed to design and optimize the DeepDOF microscope to image highly irregular tissue surfaces (up to 200 µm) at subcellular resolution without mechanical refocusing; we will combine it with fast vital dyes and deep ultraviolet illumination to achieve high contrast imaging. In Aim 2, we will carry out a clinical evaluation of DeepDOF to determine its ability to assess oral tumor margin status immediately following surgery. The clinical workflow of DeepDOF for intraoperative oral tumor margin assessment will be optimized, and its performance will be evaluated by comparing to gold standard histopathology. In Aim 3, we will develop a machine learning framework to identify positive margins in and assist annotation of large-area, cellular-resolution DeepDOF maps of oral surgical specimens. Using clinical data acquired in Aims 1 and 2, we will train an algorithm to complete segmentation tasks for identifying key diagnostic features such as nuclear enlargement and abnormal clustering; the results will be further used to annotate and quantify positive margins at the point of care. Taken together, we will develop a first microscopy platform with AI-driven optics and algorithms for rapid and slide-free histology of intact tissue samples, and we will provide important clinical evidence to show the DeepDOF platform can improve patient care during oral cancer surgeries. Equipped with a computer-aided image analysis, the broader impact of the DeepDOF platform extends to global settings including low- and middle-income countries that lack access to high quality histopathology services.

项目概要/摘要： 解剖组织病理学在疾病诊断和手术指导中发挥着核心作用，以确保 提供优质的医疗保健和治疗。例如，在手术时，肿瘤边缘理想 通过快速冰冻切片病理学进行评估，以帮助确保完全切除肿瘤，同时保留正常组织。 不幸的是，耗时和劳力密集的载玻片制备过程需要昂贵的设备和 专业人员，因此它在包括美国农村在内的许多环境中并未广泛使用；即使在设置中 在执行冰冻切片的临床基础设施中，仅手动检查一小部分边缘。在 全球环境资源有限，病理学家的严重短缺使得提供常规治疗变得更具挑战性 诊断病理学。因此，迫切需要负担得起的工具来支持高质量的组织病理学 世界各地的计划。该提案的目标是利用光学制造和 人工智能开发出一种新的、经济实惠的工具，即深度学习扩展景深 (DeepDOF) 平台，无需大量载玻片准备即可快速检查新鲜组织切除物，同时提供 护理点计算机辅助图像分析。我们将演示并验证其在肿瘤边缘的用途 对口腔鳞状细胞癌（全球第六大常见恶性肿瘤）患者的评估。 在目标 1 中，我们将开发 DeepDOF 平台的关键模块，用于对新鲜切除的细胞进行快速亚细胞成像 组织样本。将开发深度学习网络来设计和优化 DeepDOF 显微镜 以亚细胞分辨率对高度不规则的组织表面（高达 200 µm）进行成像，无需机械重新聚焦；我们 将其与快速活性染料和深紫外照明相结合，以实现高对比度成像。在目标 2 中，我们 将进行 DeepDOF 的临床评估，以确定其评估口腔肿瘤边缘状态的能力 手术后立即。 DeepDOF术中口腔肿瘤边缘的临床工作流程 优化考核，通过与金标准对比来评价其绩效 组织病理学。在目标 3 中，我们将开发一个机器学习框架来识别正利润并协助 口腔手术标本的大面积、细胞分辨率 DeepDOF 图的注释。使用临床数据 目标 1 和目标 2 中获得的数据，我们将训练一种算法来完成识别关键诊断的分割任务 核增大和异常聚集等特征；结果将进一步用于注释和 量化护理时的正利润。总之，我们将开发第一个显微镜平台 人工智能驱动的光学和算法，可对完整组织样本进行快速、无滑动的组织学分析，我们将提供 重要的临床证据表明 DeepDOF 平台可以改善口腔癌手术期间的患者护理。 配备计算机辅助图像分析，DeepDOF 平台的影响力扩展到全球 包括缺乏高质量组织病理学服务的低收入和中等收入国家的环境。